Senior AI Engineer

Collinson is a global loyalty and benefits company.

We use our expertise and products to craft customer experiences which enable some of the world’s best known brands to acquire, engage and retain the most demanding and choice-rich customers. In particular, our unique expertise and insight into high earning, frequent travellers allows us to create products and solutions for our clients that inspire greater customer engagement to drive more profitable relationships, enrich their travel experiences, protect what matters and assist in in times of need.

While specialising in Financial Services, Travel and Retail, we also support clients in multiple sectors. We have worked with over 90 airlines, 20 hotel groups and more than 600 financial institutions and banks, with clients including Accor Hotels, Air France KLM, American Express, British Airways, Cathay Pacific, Diners Club, Mandarin Oriental, Mastercard, Radisson Hotel Group, Sephora, Visa and Vhi.

We take our 30 years’ experience working with these kinds of household names in over 170 countries, and help our clients to deliver the smarter experiences it takes to differentiate their propositions, and help them win deeper devotion with their customers.

Collinson is a privately-owned entrepreneurial business with 2,000 passionate people working in 20 locations worldwide. Our solutions include Priority Pass, the world’s best known airport experiences programme, while we are also the trusted partner behind many of the leading financial services, airline and hotel brand’s reward programmes and loyalty initiatives.

Purpose of the job

As a Senior AI Engineer, you’ll play a key role in designing, building and operating AI-powered features used by real customers and colleagues at scale.

You’ll work hands-on with large language models, agentic systems and modern engineering frameworks to turn ideas into reliable, production-ready systems that deliver measurable value.

This is a practical, delivery-focused senior engineering role. You’ll take ownership across the lifecycle, from identifying high-value AI opportunities and shaping architecture, through prototyping and integration, to monitoring and improving systems once they are live.

Alongside hands-on delivery, you’ll help define reusable AI engineering patterns, provide technical guidance to other engineers and make pragmatic decisions around performance, reliability, security, privacy and cost.

You’ll be comfortable navigating uncertainty, evaluating emerging technologies and making evidence-based decisions as models, frameworks and requirements evolve.

Key Responsibilities

• AI Feature Design & Delivery – Lead the design, build and operation of AI-powered features using large language models, translating product ideas into reliable, scalable production systems that deliver measurable impact.

• LLM & Agentic System Architecture – Design integrations and architectures for LLM and agentic applications, balancing capability, performance, cost, security, reliability and maintainability.

• Technical Leadership – Provide technical direction on AI initiatives, contribute to architecture and design reviews, and help other engineers make sound technical decisions.

• Prompt Engineering & Model Optimisation – Develop, test and refine prompts, model interactions and orchestration approaches to improve accuracy, safety, latency and cost efficiency.

• Hands-On Engineering – Build and maintain backend services, APIs and AI integrations using TypeScript, Node.js and modern frameworks. Python may also be used where appropriate for AI engineering, experimentation, evaluation, data processing or integration with AI/ML tooling.

• Evaluation & Monitoring – Define and implement evaluation approaches for LLM and agentic systems, including logging, metrics and experimentation, to continuously improve quality and reliability in production.

• Scalable AI Patterns – Define and evolve reusable components, architectural patterns and engineering standards for building AI-driven and agentic capabilities across the platform.

• Security, Privacy & Cost – Make informed engineering decisions around model risk, data privacy, tool access, operational resilience and commercial constraints.

• Mentoring & Knowledge Sharing – Support engineers through code reviews, design discussions, pairing and knowledge sharing, helping raise engineering quality across the team.

• Cross-Functional Collaboration – Work closely with product, data, platform, architecture and security teams to shape solutions that are valuable, feasible and production-ready.

Knowledge, skills and experience required

Our tech stack includes TypeScript (Node.js and React), AWS, Kubernetes, DataDog, GraphQL, PostgreSQL, Mongo and Kafka. Python may also be used where appropriate for AI engineering, experimentation, evaluation and data-oriented workflows.

We’re looking for someone who brings:

• Strong software engineering experience, with a track record of designing, shipping and operating scalable, production-grade systems.

• Strong experience with TypeScript, Node.js and backend engineering, including APIs and service integration patterns.

• Practical experience with Python is beneficial, particularly for AI/ML tooling, experimentation, evaluation, data processing and AI framework integration.

• Practical experience building production applications using large language models such as OpenAI, Anthropic, Amazon Bedrock or similar.

• Experience with modern AI engineering patterns including prompt design, structured outputs, tool calling, retrieval and agentic workflows.

• Experience defining evaluation and monitoring approaches for LLM-powered systems.

• Strong understanding of cloud-native engineering, including containerisation, deployment, observability and production operations, ideally within AWS.

• Experience working with data stores such as PostgreSQL, MongoDB and/or vector databases, with an understanding of how data design supports AI-driven use cases.

• Ability to reason about architecture, cost, latency, reliability, privacy and security when designing AI-powered systems.

• Experience leading technical design discussions, contributing to architecture decisions and providing technical guidance to other engineers.

• Strong communication and collaboration skills, with the ability to explain technical concepts and trade-offs clearly to technical and non-technical stakeholders.

• Curiosity and adaptability, with the judgement to evaluate emerging AI technologies pragmatically rather than adopting them by default.

We encourage applications from people who want to grow into this role and welcome those who bring diverse perspectives, career paths, and experiences.

Nice to have

Experience in the following areas would be beneficial, but deep expertise across all of them is not required:

• Infrastructure as Code, particularly Terraform, including contributing to or extending existing modules and deployment patterns.

• Experience working within established Terraform and cloud platform standards rather than introducing parallel infrastructure patterns unnecessarily.

• AWS AI services, particularly Amazon Bedrock and Amazon Bedrock AgentCore.

• AgentCore capabilities such as Runtime, Gateway, Guardrails and agent deployment or invocation patterns.

• Model Context Protocol (MCP) servers and MCP-based integrations.

• Modern agent frameworks and orchestration approaches.

• Experience using Python for AI/ML development, model evaluation, data processing or AI framework integrations.

• IAM, networking, secrets management and CI/CD for production AI workloads.

• Building reusable AI deployment templates, platform capabilities, shared libraries or reference architectures.

• Kubernetes and containerised AI workloads.

• Production-grade, customer-facing AI or agentic services.